A deep generative model for probabilistic energy forecasting in power systems: normalizing flows (2021-06-17T00:00:00.000000Z)

TL;DR

This paper proposes to present to the power systems forecasting practitioners a recent deep learning technique, the normalizing flows, to produce accurate scenario-based probabilistic forecasts that are crucial to face the new challenges in power systems applications.

Authors

Jonathan Dumas

2 papers

Antoine Wehenkel

2 papers

Damien Lanaspeze

1 papers

Bertrand Cornélusse

1 papers

Antonio Sutera

2 papers

TL;DR

Authors

References76 items

Generative Adversarial Networks

An optimal stochastic energy management system for resilient microgrids

Multi-objective wind power scenario forecasting based on PG-GAN

A Probabilistic Forecast-Driven Strategy for a Risk-Aware Participation in the Capacity Firming Market

An introduction to deep generative modeling

Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models

Assessing the performance of deep learning models for multivariate probabilistic energy forecasting

Introduction to Normalizing Flows for Lattice Field Theory

Short-Term Forecasting of Photovoltaic Solar Power Production Using Variational Auto-Encoder Driven Deep Learning Approach

Modeling load forecast uncertainty using generative adversarial networks

Deep learning-based multi-output quantile forecasting of PV generation

Optimal configuration of concentrating solar power in multienergy power systems with an improved variational autoencoder

Complete parameter inference for GW150914 using deep learning

Graphical Normalizing Flows

Normalizing Flows: An Introduction and Review of Current Methods

Energy Forecasting: A Review and Outlook

Probabilistic solar power forecasting based on weather scenario generation

Modeling Daily Load Profiles of Distribution Network for Scenario Generation Using Flow-Based Generative Network

Day‐ahead renewable scenario forecasts based on generative adversarial networks

Normalizing Flows for Probabilistic Modeling and Inference

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Verification of solar irradiance probabilistic forecasts

Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions

Unconstrained Monotonic Neural Networks

Scenario generation of aggregated Wind, Photovoltaics and small Hydro production for power systems applications

Coordinated optimal operation of hydro–wind–solar integrated systems

Probabilistic Energy Forecasting using Quantile Regressions based on a new Nearest Neighbors Quantile Filter

Short-term scenario-based probabilistic load forecasting: A data-driven approach

Deep Learning-Based Multivariate Probabilistic Forecasting for Short-Term Scheduling in Power Markets

Demand Side Data Generating Based on Conditional Generative Adversarial Networks

Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN

Building occupancy modeling using generative adversarial network

An empirical study on evaluation metrics of generative adversarial networks

Neural Autoregressive Flows

Pros and Cons of GAN Evaluation Measures

Bayesian renewables scenario generation via deep generative networks

Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks

Estimation of the Continuous Ranked Probability Score with Limited Information and Applications to Ensemble Weather Forecasts

Parallel WaveNet: Fast High-Fidelity Speech Synthesis

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Wasserstein Generative Adversarial Networks

Masked Autoregressive Flow for Density Estimation

DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks

Improved Training of Wasserstein GANs

Towards Deeper Understanding of Variational Autoencoding Models

Towards Principled Methods for Training Generative Adversarial Networks

Probabilistic electric load forecasting: A tutorial review

Probabilistic gradient boosting machines for GEFCom2014 wind forecasting

Electric load forecasting with recency effect: A big data approach

Improved Variational Inference with Inverse Autoregressive Flow

Generation and evaluation of space–time trajectories of photovoltaic power

Variational Inference with Normalizing Flows

Variogram-Based Proper Scoring Rules for Probabilistic Forecasts of Multivariate Quantities*

Adam: A Method for Stochastic Optimization

Auto-Encoding Variational Bayes

Integrating Renewables in Electricity Markets: Operational Problems

A methodology to generate statistically dependent wind speed scenarios

Optimal Transport: Old and New

Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds

Kullback-Leibler divergence estimation of continuous distributions

Strictly Proper Scoring Rules, Prediction, and Estimation

Extremely randomized trees

Probabilistic Model of a Two-Site Wind Energy Conversion System

Probabilistic performance assessment of autonomous solar-wind energy conversion systems

Comparing Predictive Accuracy

Typical wind power scenario generation for multiple wind farms using conditional improved Wasserstein generative adversarial network

Experiment tracking with weights and biases

Optimized Operation of cascade reservoirs Considering Complementary Characteristics between wind and photovoltaic based on variational auto-encoder

Deep Learning

Strictly Proper Scoring Rules

Probabilistic forecasting

Independent consultant

From probabilistic forecasts to statistical scenarios of short-term wind power production

ROC Graphs: Notes and Practical Considerations for Researchers

25 years of time series forecasting

Testing Statistical Hypotheses

Field of Study